SOTAVerified

3D Object Detection

3D Object Detection is a task in computer vision where the goal is to identify and locate objects in a 3D environment based on their shape, location, and orientation. It involves detecting the presence of objects and determining their location in the 3D space in real-time. This task is crucial for applications such as autonomous vehicles, robotics, and augmented reality.

( Image credit: AVOD )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 951–1000 of 1576 papers

TitleStatusHype
Fully Sparse 3D Object DetectionCode2
Rethinking IoU-based Optimization for Single-stage 3D Object DetectionCode1
Det6D: A Ground-Aware Full-Pose 3D Object Detector for Improving Terrain RobustnessCode1
DID-M3D: Decoupling Instance Depth for Monocular 3D Object DetectionCode1
Consistency of Implicit and Explicit Features Matters for Monocular 3D Object Detection—0
Teachers in concordance for pseudo-labeling of 3D sequential dataCode1
Paint and Distill: Boosting 3D Object Detection with Semantic Passing NetworkCode0
Real-Time And Robust 3D Object Detection with Roadside LiDARs—0
Physical Attack on Monocular Depth Estimation with Optimal Adversarial PatchesCode1
MT-Net Submission to the Waymo 3D Detection Leaderboard—0
Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object DetectionCode1
Bounding Box Disparity: 3D Metrics for Object Detection With Full Degree of FreedomCode1
GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty EstimationCode1
CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse TransformersCode2
Boosting Single-Frame 3D Object Detection by Simulating Multi-Frame Point Clouds—0
ORA3D: Overlap Region Aware Multi-view 3D Object Detection—0
Masked Autoencoder for Self-Supervised Pre-training on Lidar Point CloudsCode1
Boosting 3D Object Detection by Simulating Multimodality on Point Clouds—0
PolarFormer: Multi-camera 3D Object Detection with Polar TransformerCode1
HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object DetectionCode1
Color-aware two-branch DCNN for efficient plant disease classificationCode1
SRCN3D: Sparse R-CNN 3D for Compact Convolutional Multi-View 3D Object Detection and TrackingCode1
Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?—0
Self-Supervised 3D Monocular Object Detection by Recycling Bounding Boxes—0
LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Network—0
LargeKernel3D: Scaling up Kernels in 3D Sparse CNNsCode2
BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object DetectionCode2
Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy AutoencodersCode2
3D Object Detection for Autonomous Driving: A Comprehensive SurveyCode2
K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather ConditionsCode2
Real3D-Aug: Point Cloud Augmentation by Placing Real Objects with Occlusion Handling for 3D Detection and SegmentationCode1
MonoGround: Detecting Monocular 3D Objects from the GroundCode1
LinK3D: Linear Keypoints Representation for 3D LiDAR Point CloudCode2
Learning Ego 3D Representation as Ray TracingCode1
Delving into the Pre-training Paradigm of Monocular 3D Object Detection—0
SpikiLi: A Spiking Simulation of LiDAR based Real-time Object Detection for Autonomous Driving—0
PETRv2: A Unified Framework for 3D Perception from Multi-Camera ImagesCode3
SparseDet: Towards End-to-End 3D Object Detection—0
Unifying Voxel-based Representation with Transformer for 3D Object DetectionCode2
LiDAR-MIMO: Efficient Uncertainty Estimation for LiDAR-based 3D Object Detection—0
Voxel Field Fusion for 3D Object DetectionCode1
itKD: Interchange Transfer-based Knowledge Distillation for 3D Object DetectionCode1
Towards Efficient 3D Object Detection with Knowledge DistillationCode1
Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object DetectionCode1
Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving—0
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingCode2
Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images—0
BEVFusion: A Simple and Robust LiDAR-Camera Fusion FrameworkCode2
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View RepresentationCode4
Structure Aware and Class Balanced 3D Object Detection on nuScenes Dataset—0
Show:102550
← PrevPage 20 of 32Next →
All datasetsnuScenesScanNetV2SUN-RGBD valKITTI Cars EasyKITTI Cars HardnuScenes Camera OnlyKITTI Cars Easy valKITTI Cars Moderate valnuscenes Camera-RadarView-of-Delft (val)KITTI Cars Hard valDAIR-V2X-I

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1EA-LSSNDS0.78—Unverified
2MegFusionNDS0.77—Unverified
3MMFusion-eNDS0.77—Unverified
4BEVFusion-eNDS0.76—Unverified
5RacoonPowerNDS0.76—Unverified
6DeepInteraction-largeNDS0.76—Unverified
7DeepInteraction-eNDS0.76—Unverified
8FusionVPENDS0.75—Unverified
9FocalFormer3D-FNDS0.75—Unverified
10CenterPoint-FusionNDS0.75—Unverified